nerui-pt-pl5-4 / trainer_state.json
apwic's picture
End of training
3858c83 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 100.0,
"eval_steps": 500,
"global_step": 9600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.1898245811462402,
"learning_rate": 4.9500000000000004e-05,
"loss": 0.8871,
"step": 96
},
{
"epoch": 1.0,
"eval_LOCATION_f1": 0.01923076923076923,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 1.0,
"eval_LOCATION_recall": 0.009708737864077669,
"eval_ORGANIZATION_f1": 0.25568181818181823,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.24861878453038674,
"eval_ORGANIZATION_recall": 0.2631578947368421,
"eval_PERSON_f1": 0.3307692307692308,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.3333333333333333,
"eval_PERSON_recall": 0.3282442748091603,
"eval_loss": 0.38537266850471497,
"eval_overall_accuracy": 0.8671637669152168,
"eval_overall_f1": 0.24860335195530722,
"eval_overall_precision": 0.2861736334405145,
"eval_overall_recall": 0.21975308641975308,
"eval_runtime": 0.2408,
"eval_samples_per_second": 706.019,
"eval_steps_per_second": 12.459,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 1.024981141090393,
"learning_rate": 4.9e-05,
"loss": 0.3506,
"step": 192
},
{
"epoch": 2.0,
"eval_LOCATION_f1": 0.4444444444444445,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.4098360655737705,
"eval_LOCATION_recall": 0.4854368932038835,
"eval_ORGANIZATION_f1": 0.6430517711171663,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.6020408163265306,
"eval_ORGANIZATION_recall": 0.6900584795321637,
"eval_PERSON_f1": 0.7915194346289753,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.7368421052631579,
"eval_PERSON_recall": 0.8549618320610687,
"eval_loss": 0.19844858348369598,
"eval_overall_accuracy": 0.9420049710024855,
"eval_overall_f1": 0.64,
"eval_overall_precision": 0.5957446808510638,
"eval_overall_recall": 0.691358024691358,
"eval_runtime": 0.2344,
"eval_samples_per_second": 725.144,
"eval_steps_per_second": 12.797,
"step": 192
},
{
"epoch": 3.0,
"grad_norm": 1.0382095575332642,
"learning_rate": 4.85e-05,
"loss": 0.1958,
"step": 288
},
{
"epoch": 3.0,
"eval_LOCATION_f1": 0.7609756097560975,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.7647058823529411,
"eval_LOCATION_recall": 0.7572815533980582,
"eval_ORGANIZATION_f1": 0.7888888888888888,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.7513227513227513,
"eval_ORGANIZATION_recall": 0.8304093567251462,
"eval_PERSON_f1": 0.966542750929368,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9420289855072463,
"eval_PERSON_recall": 0.9923664122137404,
"eval_loss": 0.10584703087806702,
"eval_overall_accuracy": 0.968240817453742,
"eval_overall_f1": 0.8393285371702638,
"eval_overall_precision": 0.8158508158508159,
"eval_overall_recall": 0.8641975308641975,
"eval_runtime": 0.2345,
"eval_samples_per_second": 724.999,
"eval_steps_per_second": 12.794,
"step": 288
},
{
"epoch": 4.0,
"grad_norm": 1.0873266458511353,
"learning_rate": 4.8e-05,
"loss": 0.1391,
"step": 384
},
{
"epoch": 4.0,
"eval_LOCATION_f1": 0.8292682926829268,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8333333333333334,
"eval_LOCATION_recall": 0.8252427184466019,
"eval_ORGANIZATION_f1": 0.8241758241758241,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.7772020725388601,
"eval_ORGANIZATION_recall": 0.8771929824561403,
"eval_PERSON_f1": 0.9660377358490565,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9552238805970149,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.08412837982177734,
"eval_overall_accuracy": 0.9734879867439934,
"eval_overall_f1": 0.8705035971223021,
"eval_overall_precision": 0.8461538461538461,
"eval_overall_recall": 0.8962962962962963,
"eval_runtime": 0.2356,
"eval_samples_per_second": 721.57,
"eval_steps_per_second": 12.734,
"step": 384
},
{
"epoch": 5.0,
"grad_norm": 0.5435639023780823,
"learning_rate": 4.75e-05,
"loss": 0.112,
"step": 480
},
{
"epoch": 5.0,
"eval_LOCATION_f1": 0.8457711442786069,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8673469387755102,
"eval_LOCATION_recall": 0.8252427184466019,
"eval_ORGANIZATION_f1": 0.8424068767908308,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8258426966292135,
"eval_ORGANIZATION_recall": 0.8596491228070176,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.07364536821842194,
"eval_overall_accuracy": 0.9768019884009942,
"eval_overall_f1": 0.8831488314883149,
"eval_overall_precision": 0.8799019607843137,
"eval_overall_recall": 0.8864197530864197,
"eval_runtime": 0.2366,
"eval_samples_per_second": 718.648,
"eval_steps_per_second": 12.682,
"step": 480
},
{
"epoch": 6.0,
"grad_norm": 3.039419174194336,
"learning_rate": 4.7e-05,
"loss": 0.0955,
"step": 576
},
{
"epoch": 6.0,
"eval_LOCATION_f1": 0.8303571428571429,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.768595041322314,
"eval_LOCATION_recall": 0.9029126213592233,
"eval_ORGANIZATION_f1": 0.8313253012048193,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8571428571428571,
"eval_ORGANIZATION_recall": 0.8070175438596491,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05852905660867691,
"eval_overall_accuracy": 0.9790113228389947,
"eval_overall_f1": 0.8742368742368742,
"eval_overall_precision": 0.8647342995169082,
"eval_overall_recall": 0.8839506172839506,
"eval_runtime": 0.2363,
"eval_samples_per_second": 719.459,
"eval_steps_per_second": 12.696,
"step": 576
},
{
"epoch": 7.0,
"grad_norm": 0.8530810475349426,
"learning_rate": 4.6500000000000005e-05,
"loss": 0.083,
"step": 672
},
{
"epoch": 7.0,
"eval_LOCATION_f1": 0.8866995073891626,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.8737864077669902,
"eval_ORGANIZATION_f1": 0.8950276243093923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8481675392670157,
"eval_ORGANIZATION_recall": 0.9473684210526315,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.0581318736076355,
"eval_overall_accuracy": 0.9831538249102458,
"eval_overall_f1": 0.9154589371980677,
"eval_overall_precision": 0.8959810874704491,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2344,
"eval_samples_per_second": 725.172,
"eval_steps_per_second": 12.797,
"step": 672
},
{
"epoch": 8.0,
"grad_norm": 0.25684356689453125,
"learning_rate": 4.600000000000001e-05,
"loss": 0.0751,
"step": 768
},
{
"epoch": 8.0,
"eval_LOCATION_f1": 0.8811881188118812,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.898989898989899,
"eval_LOCATION_recall": 0.8640776699029126,
"eval_ORGANIZATION_f1": 0.8833333333333334,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8412698412698413,
"eval_ORGANIZATION_recall": 0.9298245614035088,
"eval_PERSON_f1": 0.9696969696969696,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9624060150375939,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04575686156749725,
"eval_overall_accuracy": 0.9848108257387462,
"eval_overall_f1": 0.910411622276029,
"eval_overall_precision": 0.8931116389548693,
"eval_overall_recall": 0.928395061728395,
"eval_runtime": 0.2351,
"eval_samples_per_second": 723.112,
"eval_steps_per_second": 12.761,
"step": 768
},
{
"epoch": 9.0,
"grad_norm": 0.6107448935508728,
"learning_rate": 4.55e-05,
"loss": 0.0713,
"step": 864
},
{
"epoch": 9.0,
"eval_LOCATION_f1": 0.8878923766816144,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.825,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.8700906344410877,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9,
"eval_ORGANIZATION_recall": 0.8421052631578947,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.050280213356018066,
"eval_overall_accuracy": 0.983982325324496,
"eval_overall_f1": 0.908200734394125,
"eval_overall_precision": 0.9004854368932039,
"eval_overall_recall": 0.9160493827160494,
"eval_runtime": 0.2357,
"eval_samples_per_second": 721.111,
"eval_steps_per_second": 12.725,
"step": 864
},
{
"epoch": 10.0,
"grad_norm": 0.8482660055160522,
"learning_rate": 4.5e-05,
"loss": 0.0655,
"step": 960
},
{
"epoch": 10.0,
"eval_LOCATION_f1": 0.9289099526066351,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9074074074074074,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9195402298850573,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.903954802259887,
"eval_ORGANIZATION_recall": 0.935672514619883,
"eval_PERSON_f1": 0.9735849056603774,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9626865671641791,
"eval_PERSON_recall": 0.9847328244274809,
"eval_loss": 0.042979221791028976,
"eval_overall_accuracy": 0.9872963269814968,
"eval_overall_f1": 0.9393203883495146,
"eval_overall_precision": 0.9236276849642004,
"eval_overall_recall": 0.9555555555555556,
"eval_runtime": 0.2354,
"eval_samples_per_second": 722.084,
"eval_steps_per_second": 12.743,
"step": 960
},
{
"epoch": 11.0,
"grad_norm": 0.7679306864738464,
"learning_rate": 4.4500000000000004e-05,
"loss": 0.063,
"step": 1056
},
{
"epoch": 11.0,
"eval_LOCATION_f1": 0.9261083743842364,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.94,
"eval_LOCATION_recall": 0.912621359223301,
"eval_ORGANIZATION_f1": 0.9096045197740114,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8797814207650273,
"eval_ORGANIZATION_recall": 0.9415204678362573,
"eval_PERSON_f1": 0.9808429118773947,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9846153846153847,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.038064610213041306,
"eval_overall_accuracy": 0.9867439933719967,
"eval_overall_f1": 0.9364303178484108,
"eval_overall_precision": 0.927360774818402,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2359,
"eval_samples_per_second": 720.513,
"eval_steps_per_second": 12.715,
"step": 1056
},
{
"epoch": 12.0,
"grad_norm": 0.7759473323822021,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.0577,
"step": 1152
},
{
"epoch": 12.0,
"eval_LOCATION_f1": 0.9365853658536586,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9411764705882353,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.9065155807365438,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8791208791208791,
"eval_ORGANIZATION_recall": 0.935672514619883,
"eval_PERSON_f1": 0.9696969696969696,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9624060150375939,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.039730243384838104,
"eval_overall_accuracy": 0.9864678265672466,
"eval_overall_f1": 0.9343065693430658,
"eval_overall_precision": 0.920863309352518,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.234,
"eval_samples_per_second": 726.38,
"eval_steps_per_second": 12.818,
"step": 1152
},
{
"epoch": 13.0,
"grad_norm": 1.3981506824493408,
"learning_rate": 4.35e-05,
"loss": 0.0562,
"step": 1248
},
{
"epoch": 13.0,
"eval_LOCATION_f1": 0.888888888888889,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8495575221238938,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.8823529411764705,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8875739644970414,
"eval_ORGANIZATION_recall": 0.8771929824561403,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.042980071157217026,
"eval_overall_accuracy": 0.9842584921292461,
"eval_overall_f1": 0.9133089133089134,
"eval_overall_precision": 0.9033816425120773,
"eval_overall_recall": 0.9234567901234568,
"eval_runtime": 0.2352,
"eval_samples_per_second": 722.891,
"eval_steps_per_second": 12.757,
"step": 1248
},
{
"epoch": 14.0,
"grad_norm": 0.48644790053367615,
"learning_rate": 4.3e-05,
"loss": 0.0518,
"step": 1344
},
{
"epoch": 14.0,
"eval_LOCATION_f1": 0.9194312796208531,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8981481481481481,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.8994082840236686,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9101796407185628,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04729074984788895,
"eval_overall_accuracy": 0.9850869925434963,
"eval_overall_f1": 0.9285714285714285,
"eval_overall_precision": 0.9262899262899262,
"eval_overall_recall": 0.9308641975308642,
"eval_runtime": 0.2349,
"eval_samples_per_second": 723.593,
"eval_steps_per_second": 12.769,
"step": 1344
},
{
"epoch": 15.0,
"grad_norm": 0.9471101760864258,
"learning_rate": 4.25e-05,
"loss": 0.0517,
"step": 1440
},
{
"epoch": 15.0,
"eval_LOCATION_f1": 0.9268292682926829,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9313725490196079,
"eval_LOCATION_recall": 0.9223300970873787,
"eval_ORGANIZATION_f1": 0.8870056497175142,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8579234972677595,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9772727272727273,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9699248120300752,
"eval_PERSON_recall": 0.9847328244274809,
"eval_loss": 0.04410385340452194,
"eval_overall_accuracy": 0.9853631593482464,
"eval_overall_f1": 0.9258809234507898,
"eval_overall_precision": 0.9114832535885168,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2355,
"eval_samples_per_second": 721.995,
"eval_steps_per_second": 12.741,
"step": 1440
},
{
"epoch": 16.0,
"grad_norm": 0.7192522883415222,
"learning_rate": 4.2e-05,
"loss": 0.0505,
"step": 1536
},
{
"epoch": 16.0,
"eval_LOCATION_f1": 0.9142857142857143,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.897196261682243,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.8895348837209303,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.884393063583815,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.040617913007736206,
"eval_overall_accuracy": 0.9850869925434963,
"eval_overall_f1": 0.9240196078431373,
"eval_overall_precision": 0.9172749391727494,
"eval_overall_recall": 0.9308641975308642,
"eval_runtime": 0.2343,
"eval_samples_per_second": 725.692,
"eval_steps_per_second": 12.806,
"step": 1536
},
{
"epoch": 17.0,
"grad_norm": 0.4512641131877899,
"learning_rate": 4.15e-05,
"loss": 0.0447,
"step": 1632
},
{
"epoch": 17.0,
"eval_LOCATION_f1": 0.9150943396226414,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8899082568807339,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9037900874635568,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9011627906976745,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.039824921637773514,
"eval_overall_accuracy": 0.9870201601767468,
"eval_overall_f1": 0.9290953545232274,
"eval_overall_precision": 0.9200968523002422,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2348,
"eval_samples_per_second": 723.956,
"eval_steps_per_second": 12.776,
"step": 1632
},
{
"epoch": 18.0,
"grad_norm": 0.5407056212425232,
"learning_rate": 4.1e-05,
"loss": 0.0411,
"step": 1728
},
{
"epoch": 18.0,
"eval_LOCATION_f1": 0.9158878504672898,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8828828828828829,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.8979591836734693,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8953488372093024,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.040666572749614716,
"eval_overall_accuracy": 0.9853631593482464,
"eval_overall_f1": 0.9279609279609279,
"eval_overall_precision": 0.9178743961352657,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2343,
"eval_samples_per_second": 725.542,
"eval_steps_per_second": 12.804,
"step": 1728
},
{
"epoch": 19.0,
"grad_norm": 0.37152308225631714,
"learning_rate": 4.05e-05,
"loss": 0.0413,
"step": 1824
},
{
"epoch": 19.0,
"eval_LOCATION_f1": 0.9339622641509433,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.908256880733945,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9149560117302051,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9176470588235294,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03785136714577675,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.939877300613497,
"eval_overall_precision": 0.9341463414634147,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2351,
"eval_samples_per_second": 723.183,
"eval_steps_per_second": 12.762,
"step": 1824
},
{
"epoch": 20.0,
"grad_norm": 0.3923741579055786,
"learning_rate": 4e-05,
"loss": 0.0392,
"step": 1920
},
{
"epoch": 20.0,
"eval_LOCATION_f1": 0.9345794392523364,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9009009009009009,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9171597633136095,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04119547829031944,
"eval_overall_accuracy": 0.9870201601767468,
"eval_overall_f1": 0.939877300613497,
"eval_overall_precision": 0.9341463414634147,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2354,
"eval_samples_per_second": 722.22,
"eval_steps_per_second": 12.745,
"step": 1920
},
{
"epoch": 21.0,
"grad_norm": 0.4528615474700928,
"learning_rate": 3.9500000000000005e-05,
"loss": 0.0383,
"step": 2016
},
{
"epoch": 21.0,
"eval_LOCATION_f1": 0.9333333333333335,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9158878504672897,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9212827988338192,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9186046511627907,
"eval_ORGANIZATION_recall": 0.9239766081871345,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03925593942403793,
"eval_overall_accuracy": 0.9872963269814968,
"eval_overall_f1": 0.939877300613497,
"eval_overall_precision": 0.9341463414634147,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2363,
"eval_samples_per_second": 719.477,
"eval_steps_per_second": 12.697,
"step": 2016
},
{
"epoch": 22.0,
"grad_norm": 0.9368549585342407,
"learning_rate": 3.9000000000000006e-05,
"loss": 0.0381,
"step": 2112
},
{
"epoch": 22.0,
"eval_LOCATION_f1": 0.9295774647887324,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9271137026239067,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9244186046511628,
"eval_ORGANIZATION_recall": 0.9298245614035088,
"eval_PERSON_f1": 0.9696969696969696,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9624060150375939,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.03787771239876747,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9414634146341463,
"eval_overall_precision": 0.9301204819277108,
"eval_overall_recall": 0.9530864197530864,
"eval_runtime": 0.2339,
"eval_samples_per_second": 726.768,
"eval_steps_per_second": 12.825,
"step": 2112
},
{
"epoch": 23.0,
"grad_norm": 0.8920877575874329,
"learning_rate": 3.85e-05,
"loss": 0.0368,
"step": 2208
},
{
"epoch": 23.0,
"eval_LOCATION_f1": 0.9289099526066351,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9074074074074074,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.8895348837209303,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.884393063583815,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.041652414947748184,
"eval_overall_accuracy": 0.9864678265672466,
"eval_overall_f1": 0.9253365973072215,
"eval_overall_precision": 0.9174757281553398,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.2345,
"eval_samples_per_second": 724.805,
"eval_steps_per_second": 12.791,
"step": 2208
},
{
"epoch": 24.0,
"grad_norm": 1.1886273622512817,
"learning_rate": 3.8e-05,
"loss": 0.0354,
"step": 2304
},
{
"epoch": 24.0,
"eval_LOCATION_f1": 0.9333333333333335,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9158878504672897,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9026548672566371,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9107142857142857,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.042355556041002274,
"eval_overall_accuracy": 0.9864678265672466,
"eval_overall_f1": 0.9321824907521578,
"eval_overall_precision": 0.9310344827586207,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.234,
"eval_samples_per_second": 726.417,
"eval_steps_per_second": 12.819,
"step": 2304
},
{
"epoch": 25.0,
"grad_norm": 0.3123241066932678,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.0345,
"step": 2400
},
{
"epoch": 25.0,
"eval_LOCATION_f1": 0.9345794392523364,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9009009009009009,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.8994082840236686,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9101796407185628,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03874532878398895,
"eval_overall_accuracy": 0.9864678265672466,
"eval_overall_f1": 0.9312039312039312,
"eval_overall_precision": 0.9266503667481663,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2356,
"eval_samples_per_second": 721.528,
"eval_steps_per_second": 12.733,
"step": 2400
},
{
"epoch": 26.0,
"grad_norm": 0.6889738440513611,
"learning_rate": 3.7e-05,
"loss": 0.0332,
"step": 2496
},
{
"epoch": 26.0,
"eval_LOCATION_f1": 0.9253731343283583,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9489795918367347,
"eval_LOCATION_recall": 0.9029126213592233,
"eval_ORGANIZATION_f1": 0.8977272727272728,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8729281767955801,
"eval_ORGANIZATION_recall": 0.9239766081871345,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.039866361767053604,
"eval_overall_accuracy": 0.9867439933719967,
"eval_overall_f1": 0.9289215686274509,
"eval_overall_precision": 0.9221411192214112,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2341,
"eval_samples_per_second": 726.204,
"eval_steps_per_second": 12.815,
"step": 2496
},
{
"epoch": 27.0,
"grad_norm": 0.9042752981185913,
"learning_rate": 3.65e-05,
"loss": 0.0333,
"step": 2592
},
{
"epoch": 27.0,
"eval_LOCATION_f1": 0.9230769230769231,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9142857142857143,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.9069767441860466,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9017341040462428,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.0369257926940918,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.9336609336609337,
"eval_overall_precision": 0.9290953545232273,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.235,
"eval_samples_per_second": 723.537,
"eval_steps_per_second": 12.768,
"step": 2592
},
{
"epoch": 28.0,
"grad_norm": 0.5801326036453247,
"learning_rate": 3.6e-05,
"loss": 0.0324,
"step": 2688
},
{
"epoch": 28.0,
"eval_LOCATION_f1": 0.9458128078817734,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.96,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.925287356321839,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9096045197740112,
"eval_ORGANIZATION_recall": 0.9415204678362573,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03761325031518936,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9446494464944649,
"eval_overall_precision": 0.9411764705882353,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2345,
"eval_samples_per_second": 724.909,
"eval_steps_per_second": 12.793,
"step": 2688
},
{
"epoch": 29.0,
"grad_norm": 0.7175154685974121,
"learning_rate": 3.55e-05,
"loss": 0.0299,
"step": 2784
},
{
"epoch": 29.0,
"eval_LOCATION_f1": 0.9252336448598131,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8918918918918919,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9171597633136095,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03826238587498665,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.9361179361179361,
"eval_overall_precision": 0.9315403422982885,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2349,
"eval_samples_per_second": 723.791,
"eval_steps_per_second": 12.773,
"step": 2784
},
{
"epoch": 30.0,
"grad_norm": 0.3616092801094055,
"learning_rate": 3.5e-05,
"loss": 0.0299,
"step": 2880
},
{
"epoch": 30.0,
"eval_LOCATION_f1": 0.9365853658536586,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9411764705882353,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.9022988505747127,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8870056497175142,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04245363175868988,
"eval_overall_accuracy": 0.9867439933719967,
"eval_overall_f1": 0.9313725490196078,
"eval_overall_precision": 0.9245742092457421,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2346,
"eval_samples_per_second": 724.694,
"eval_steps_per_second": 12.789,
"step": 2880
},
{
"epoch": 31.0,
"grad_norm": 0.4774545133113861,
"learning_rate": 3.45e-05,
"loss": 0.0276,
"step": 2976
},
{
"epoch": 31.0,
"eval_LOCATION_f1": 0.9289099526066351,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9074074074074074,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9053254437869822,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03856751322746277,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9321824907521578,
"eval_overall_precision": 0.9310344827586207,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.2348,
"eval_samples_per_second": 724.024,
"eval_steps_per_second": 12.777,
"step": 2976
},
{
"epoch": 32.0,
"grad_norm": 1.1690179109573364,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.0281,
"step": 3072
},
{
"epoch": 32.0,
"eval_LOCATION_f1": 0.9259259259259259,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8849557522123894,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9063444108761328,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9375,
"eval_ORGANIZATION_recall": 0.8771929824561403,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03932028263807297,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9320148331273176,
"eval_overall_precision": 0.9331683168316832,
"eval_overall_recall": 0.9308641975308642,
"eval_runtime": 0.235,
"eval_samples_per_second": 723.256,
"eval_steps_per_second": 12.763,
"step": 3072
},
{
"epoch": 33.0,
"grad_norm": 0.16415248811244965,
"learning_rate": 3.35e-05,
"loss": 0.0244,
"step": 3168
},
{
"epoch": 33.0,
"eval_LOCATION_f1": 0.9439252336448598,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9099099099099099,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9212121212121211,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9559748427672956,
"eval_ORGANIZATION_recall": 0.8888888888888888,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.040390245616436005,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9429280397022332,
"eval_overall_precision": 0.9476309226932669,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2356,
"eval_samples_per_second": 721.469,
"eval_steps_per_second": 12.732,
"step": 3168
},
{
"epoch": 34.0,
"grad_norm": 0.5438923835754395,
"learning_rate": 3.3e-05,
"loss": 0.0266,
"step": 3264
},
{
"epoch": 34.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9137931034482759,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8983050847457628,
"eval_ORGANIZATION_recall": 0.9298245614035088,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03569287434220314,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9364303178484108,
"eval_overall_precision": 0.927360774818402,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2354,
"eval_samples_per_second": 722.119,
"eval_steps_per_second": 12.743,
"step": 3264
},
{
"epoch": 35.0,
"grad_norm": 0.26597175002098083,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.0255,
"step": 3360
},
{
"epoch": 35.0,
"eval_LOCATION_f1": 0.9383886255924171,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.913946587537092,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.041076935827732086,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9371146732429099,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2341,
"eval_samples_per_second": 726.292,
"eval_steps_per_second": 12.817,
"step": 3360
},
{
"epoch": 36.0,
"grad_norm": 0.7941347360610962,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.0243,
"step": 3456
},
{
"epoch": 36.0,
"eval_LOCATION_f1": 0.9383886255924171,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.8908554572271385,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8988095238095238,
"eval_ORGANIZATION_recall": 0.8830409356725146,
"eval_PERSON_f1": 0.9618320610687023,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9618320610687023,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.040873657912015915,
"eval_overall_accuracy": 0.9872963269814968,
"eval_overall_f1": 0.9261083743842363,
"eval_overall_precision": 0.9238329238329238,
"eval_overall_recall": 0.928395061728395,
"eval_runtime": 0.2345,
"eval_samples_per_second": 724.857,
"eval_steps_per_second": 12.792,
"step": 3456
},
{
"epoch": 37.0,
"grad_norm": 0.9714059829711914,
"learning_rate": 3.15e-05,
"loss": 0.0227,
"step": 3552
},
{
"epoch": 37.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9173789173789174,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8944444444444445,
"eval_ORGANIZATION_recall": 0.9415204678362573,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.045831140130758286,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9390243902439024,
"eval_overall_precision": 0.927710843373494,
"eval_overall_recall": 0.9506172839506173,
"eval_runtime": 0.2344,
"eval_samples_per_second": 725.222,
"eval_steps_per_second": 12.798,
"step": 3552
},
{
"epoch": 38.0,
"grad_norm": 0.8643996119499207,
"learning_rate": 3.1e-05,
"loss": 0.0244,
"step": 3648
},
{
"epoch": 38.0,
"eval_LOCATION_f1": 0.9245283018867926,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8990825688073395,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.8835820895522388,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9024390243902439,
"eval_ORGANIZATION_recall": 0.8654970760233918,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04439312219619751,
"eval_overall_accuracy": 0.9861916597624966,
"eval_overall_f1": 0.9209876543209876,
"eval_overall_precision": 0.9209876543209876,
"eval_overall_recall": 0.9209876543209876,
"eval_runtime": 0.2349,
"eval_samples_per_second": 723.729,
"eval_steps_per_second": 12.772,
"step": 3648
},
{
"epoch": 39.0,
"grad_norm": 0.629501461982727,
"learning_rate": 3.05e-05,
"loss": 0.024,
"step": 3744
},
{
"epoch": 39.0,
"eval_LOCATION_f1": 0.9320388349514563,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9320388349514563,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.8921282798833821,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8895348837209303,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.03887235000729561,
"eval_overall_accuracy": 0.9872963269814968,
"eval_overall_f1": 0.9261083743842363,
"eval_overall_precision": 0.9238329238329238,
"eval_overall_recall": 0.928395061728395,
"eval_runtime": 0.2356,
"eval_samples_per_second": 721.496,
"eval_steps_per_second": 12.732,
"step": 3744
},
{
"epoch": 40.0,
"grad_norm": 0.26163867115974426,
"learning_rate": 3e-05,
"loss": 0.0228,
"step": 3840
},
{
"epoch": 40.0,
"eval_LOCATION_f1": 0.9383886255924171,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9166666666666666,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.8869047619047619,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9030303030303031,
"eval_ORGANIZATION_recall": 0.8713450292397661,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.047314707189798355,
"eval_overall_accuracy": 0.9864678265672466,
"eval_overall_f1": 0.9259259259259259,
"eval_overall_precision": 0.9259259259259259,
"eval_overall_recall": 0.9259259259259259,
"eval_runtime": 0.236,
"eval_samples_per_second": 720.398,
"eval_steps_per_second": 12.713,
"step": 3840
},
{
"epoch": 41.0,
"grad_norm": 1.863937258720398,
"learning_rate": 2.95e-05,
"loss": 0.0226,
"step": 3936
},
{
"epoch": 41.0,
"eval_LOCATION_f1": 0.9246231155778895,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9583333333333334,
"eval_LOCATION_recall": 0.8932038834951457,
"eval_ORGANIZATION_f1": 0.8914285714285715,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.8715083798882681,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04839714989066124,
"eval_overall_accuracy": 0.9856393261529964,
"eval_overall_f1": 0.9236453201970444,
"eval_overall_precision": 0.9213759213759214,
"eval_overall_recall": 0.9259259259259259,
"eval_runtime": 0.2346,
"eval_samples_per_second": 724.772,
"eval_steps_per_second": 12.79,
"step": 3936
},
{
"epoch": 42.0,
"grad_norm": 0.19347354769706726,
"learning_rate": 2.9e-05,
"loss": 0.0221,
"step": 4032
},
{
"epoch": 42.0,
"eval_LOCATION_f1": 0.9320388349514563,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9320388349514563,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.9090909090909091,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9117647058823529,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04077206552028656,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.9333333333333333,
"eval_overall_precision": 0.9333333333333333,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.234,
"eval_samples_per_second": 726.463,
"eval_steps_per_second": 12.82,
"step": 4032
},
{
"epoch": 43.0,
"grad_norm": 0.4478389024734497,
"learning_rate": 2.8499999999999998e-05,
"loss": 0.0195,
"step": 4128
},
{
"epoch": 43.0,
"eval_LOCATION_f1": 0.9389671361502346,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.8934911242603552,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9041916167664671,
"eval_ORGANIZATION_recall": 0.8830409356725146,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.0387241467833519,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.9287469287469288,
"eval_overall_precision": 0.9242053789731052,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.235,
"eval_samples_per_second": 723.51,
"eval_steps_per_second": 12.768,
"step": 4128
},
{
"epoch": 44.0,
"grad_norm": 1.0307210683822632,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.0204,
"step": 4224
},
{
"epoch": 44.0,
"eval_LOCATION_f1": 0.9377990430622011,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9245283018867925,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9171597633136095,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9281437125748503,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9618320610687023,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9618320610687023,
"eval_PERSON_recall": 0.9618320610687023,
"eval_loss": 0.046855658292770386,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9369592088998763,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2362,
"eval_samples_per_second": 719.689,
"eval_steps_per_second": 12.7,
"step": 4224
},
{
"epoch": 45.0,
"grad_norm": 0.4691741168498993,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.0216,
"step": 4320
},
{
"epoch": 45.0,
"eval_LOCATION_f1": 0.9488372093023257,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9107142857142857,
"eval_LOCATION_recall": 0.9902912621359223,
"eval_ORGANIZATION_f1": 0.9134328358208956,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9329268292682927,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04813939705491066,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9421894218942188,
"eval_overall_precision": 0.9387254901960784,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2342,
"eval_samples_per_second": 725.779,
"eval_steps_per_second": 12.808,
"step": 4320
},
{
"epoch": 46.0,
"grad_norm": 0.256936252117157,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.0199,
"step": 4416
},
{
"epoch": 46.0,
"eval_LOCATION_f1": 0.9433962264150944,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9174311926605505,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9053254437869822,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04166381433606148,
"eval_overall_accuracy": 0.9872963269814968,
"eval_overall_f1": 0.938423645320197,
"eval_overall_precision": 0.9361179361179361,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2336,
"eval_samples_per_second": 727.68,
"eval_steps_per_second": 12.841,
"step": 4416
},
{
"epoch": 47.0,
"grad_norm": 0.3251420855522156,
"learning_rate": 2.6500000000000004e-05,
"loss": 0.021,
"step": 4512
},
{
"epoch": 47.0,
"eval_LOCATION_f1": 0.9333333333333335,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9158878504672897,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9085545722713864,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9166666666666666,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04079382121562958,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9371146732429099,
"eval_overall_precision": 0.9359605911330049,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2342,
"eval_samples_per_second": 725.745,
"eval_steps_per_second": 12.807,
"step": 4512
},
{
"epoch": 48.0,
"grad_norm": 1.2281031608581543,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.0201,
"step": 4608
},
{
"epoch": 48.0,
"eval_LOCATION_f1": 0.9252336448598131,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.8918918918918919,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.8835820895522388,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9024390243902439,
"eval_ORGANIZATION_recall": 0.8654970760233918,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04934144392609596,
"eval_overall_accuracy": 0.9875724937862469,
"eval_overall_f1": 0.9247842170160296,
"eval_overall_precision": 0.9236453201970444,
"eval_overall_recall": 0.9259259259259259,
"eval_runtime": 0.2344,
"eval_samples_per_second": 725.129,
"eval_steps_per_second": 12.796,
"step": 4608
},
{
"epoch": 49.0,
"grad_norm": 0.033093735575675964,
"learning_rate": 2.5500000000000003e-05,
"loss": 0.0203,
"step": 4704
},
{
"epoch": 49.0,
"eval_LOCATION_f1": 0.9289099526066351,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9074074074074074,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9107142857142856,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04231979325413704,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9369592088998763,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2335,
"eval_samples_per_second": 728.04,
"eval_steps_per_second": 12.848,
"step": 4704
},
{
"epoch": 50.0,
"grad_norm": 0.6893525123596191,
"learning_rate": 2.5e-05,
"loss": 0.0197,
"step": 4800
},
{
"epoch": 50.0,
"eval_LOCATION_f1": 0.9423076923076923,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9154518950437317,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9127906976744186,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04348357021808624,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9410319410319411,
"eval_overall_precision": 0.9364303178484108,
"eval_overall_recall": 0.945679012345679,
"eval_runtime": 0.2348,
"eval_samples_per_second": 724.102,
"eval_steps_per_second": 12.778,
"step": 4800
},
{
"epoch": 51.0,
"grad_norm": 0.47854194045066833,
"learning_rate": 2.45e-05,
"loss": 0.0184,
"step": 4896
},
{
"epoch": 51.0,
"eval_LOCATION_f1": 0.9389671361502346,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9107142857142856,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9272727272727272,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04116761311888695,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.938423645320197,
"eval_overall_precision": 0.9361179361179361,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2346,
"eval_samples_per_second": 724.519,
"eval_steps_per_second": 12.786,
"step": 4896
},
{
"epoch": 52.0,
"grad_norm": 0.3364722430706024,
"learning_rate": 2.4e-05,
"loss": 0.0197,
"step": 4992
},
{
"epoch": 52.0,
"eval_LOCATION_f1": 0.9377990430622011,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9245283018867925,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9053254437869822,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9161676646706587,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.040494710206985474,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9358024691358025,
"eval_overall_precision": 0.9358024691358025,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2343,
"eval_samples_per_second": 725.48,
"eval_steps_per_second": 12.803,
"step": 4992
},
{
"epoch": 53.0,
"grad_norm": 0.23096852004528046,
"learning_rate": 2.35e-05,
"loss": 0.0187,
"step": 5088
},
{
"epoch": 53.0,
"eval_LOCATION_f1": 0.9377990430622011,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9245283018867925,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9005847953216374,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9005847953216374,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.041741449385881424,
"eval_overall_accuracy": 0.9872963269814968,
"eval_overall_f1": 0.9336609336609337,
"eval_overall_precision": 0.9290953545232273,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.237,
"eval_samples_per_second": 717.438,
"eval_steps_per_second": 12.661,
"step": 5088
},
{
"epoch": 54.0,
"grad_norm": 0.3252106308937073,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.0175,
"step": 5184
},
{
"epoch": 54.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9005847953216374,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9005847953216374,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04329456016421318,
"eval_overall_accuracy": 0.9864678265672466,
"eval_overall_f1": 0.9334975369458127,
"eval_overall_precision": 0.9312039312039312,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2354,
"eval_samples_per_second": 722.322,
"eval_steps_per_second": 12.747,
"step": 5184
},
{
"epoch": 55.0,
"grad_norm": 0.7962756156921387,
"learning_rate": 2.25e-05,
"loss": 0.0195,
"step": 5280
},
{
"epoch": 55.0,
"eval_LOCATION_f1": 0.9395348837209301,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9017857142857143,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9161676646706587,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9386503067484663,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04764256253838539,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9420468557336621,
"eval_overall_precision": 0.9408866995073891,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.239,
"eval_samples_per_second": 711.359,
"eval_steps_per_second": 12.553,
"step": 5280
},
{
"epoch": 56.0,
"grad_norm": 0.40496009588241577,
"learning_rate": 2.2000000000000003e-05,
"loss": 0.0176,
"step": 5376
},
{
"epoch": 56.0,
"eval_LOCATION_f1": 0.9326923076923078,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9238095238095239,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9085545722713864,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9166666666666666,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04565516859292984,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9369592088998763,
"eval_overall_precision": 0.9381188118811881,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2351,
"eval_samples_per_second": 722.997,
"eval_steps_per_second": 12.759,
"step": 5376
},
{
"epoch": 57.0,
"grad_norm": 0.4700881838798523,
"learning_rate": 2.15e-05,
"loss": 0.0175,
"step": 5472
},
{
"epoch": 57.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9176470588235294,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9230769230769231,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9660377358490565,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9552238805970149,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04221116378903389,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.938423645320197,
"eval_overall_precision": 0.9361179361179361,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2346,
"eval_samples_per_second": 724.598,
"eval_steps_per_second": 12.787,
"step": 5472
},
{
"epoch": 58.0,
"grad_norm": 0.13470809161663055,
"learning_rate": 2.1e-05,
"loss": 0.0171,
"step": 5568
},
{
"epoch": 58.0,
"eval_LOCATION_f1": 0.9333333333333335,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9158878504672897,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9161676646706587,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9386503067484663,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9733840304182511,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9696969696969697,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04665978252887726,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9392812887236679,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2341,
"eval_samples_per_second": 726.161,
"eval_steps_per_second": 12.815,
"step": 5568
},
{
"epoch": 59.0,
"grad_norm": 2.558548927307129,
"learning_rate": 2.05e-05,
"loss": 0.0165,
"step": 5664
},
{
"epoch": 59.0,
"eval_LOCATION_f1": 0.9433962264150944,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9174311926605505,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9194029850746269,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9390243902439024,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9696969696969696,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9624060150375939,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.045579176396131516,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9420468557336621,
"eval_overall_precision": 0.9408866995073891,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2351,
"eval_samples_per_second": 723.236,
"eval_steps_per_second": 12.763,
"step": 5664
},
{
"epoch": 60.0,
"grad_norm": 0.11199408769607544,
"learning_rate": 2e-05,
"loss": 0.0173,
"step": 5760
},
{
"epoch": 60.0,
"eval_LOCATION_f1": 0.9389671361502346,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9090909090909091,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9161676646706587,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9386503067484663,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.048589516431093216,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9419035846724351,
"eval_overall_precision": 0.943069306930693,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2335,
"eval_samples_per_second": 727.953,
"eval_steps_per_second": 12.846,
"step": 5760
},
{
"epoch": 61.0,
"grad_norm": 0.5329948663711548,
"learning_rate": 1.9500000000000003e-05,
"loss": 0.0155,
"step": 5856
},
{
"epoch": 61.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9117647058823529,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9171597633136095,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.043716032058000565,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9394313967861556,
"eval_overall_precision": 0.9405940594059405,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.235,
"eval_samples_per_second": 723.472,
"eval_steps_per_second": 12.767,
"step": 5856
},
{
"epoch": 62.0,
"grad_norm": 1.395460605621338,
"learning_rate": 1.9e-05,
"loss": 0.0151,
"step": 5952
},
{
"epoch": 62.0,
"eval_LOCATION_f1": 0.9339622641509433,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.908256880733945,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.913946587537092,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.927710843373494,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9696969696969696,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9624060150375939,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.052707403898239136,
"eval_overall_accuracy": 0.987848660590997,
"eval_overall_f1": 0.9372693726937269,
"eval_overall_precision": 0.9338235294117647,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2352,
"eval_samples_per_second": 722.838,
"eval_steps_per_second": 12.756,
"step": 5952
},
{
"epoch": 63.0,
"grad_norm": 0.4671809673309326,
"learning_rate": 1.85e-05,
"loss": 0.0171,
"step": 6048
},
{
"epoch": 63.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9194029850746269,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9390243902439024,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04843275249004364,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9442379182156135,
"eval_overall_precision": 0.9477611940298507,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.233,
"eval_samples_per_second": 729.638,
"eval_steps_per_second": 12.876,
"step": 6048
},
{
"epoch": 64.0,
"grad_norm": 0.3749203383922577,
"learning_rate": 1.8e-05,
"loss": 0.0151,
"step": 6144
},
{
"epoch": 64.0,
"eval_LOCATION_f1": 0.9433962264150944,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9174311926605505,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.918918918918919,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9444444444444444,
"eval_ORGANIZATION_recall": 0.8947368421052632,
"eval_PERSON_f1": 0.9731800766283524,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9769230769230769,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04646661505103111,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9429280397022332,
"eval_overall_precision": 0.9476309226932669,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2359,
"eval_samples_per_second": 720.739,
"eval_steps_per_second": 12.719,
"step": 6144
},
{
"epoch": 65.0,
"grad_norm": 0.3341313302516937,
"learning_rate": 1.75e-05,
"loss": 0.0146,
"step": 6240
},
{
"epoch": 65.0,
"eval_LOCATION_f1": 0.9473684210526316,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9339622641509434,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9258160237388725,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9397590361445783,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.962121212121212,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9548872180451128,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.048213183879852295,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9432098765432099,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2335,
"eval_samples_per_second": 727.965,
"eval_steps_per_second": 12.846,
"step": 6240
},
{
"epoch": 66.0,
"grad_norm": 0.2666481137275696,
"learning_rate": 1.7000000000000003e-05,
"loss": 0.0141,
"step": 6336
},
{
"epoch": 66.0,
"eval_LOCATION_f1": 0.9439252336448598,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9099099099099099,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9221556886227544,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9447852760736196,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.047435760498046875,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9432098765432099,
"eval_overall_precision": 0.9432098765432099,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2347,
"eval_samples_per_second": 724.267,
"eval_steps_per_second": 12.781,
"step": 6336
},
{
"epoch": 67.0,
"grad_norm": 0.02973143756389618,
"learning_rate": 1.65e-05,
"loss": 0.015,
"step": 6432
},
{
"epoch": 67.0,
"eval_LOCATION_f1": 0.9528301886792453,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.926605504587156,
"eval_LOCATION_recall": 0.9805825242718447,
"eval_ORGANIZATION_f1": 0.9285714285714285,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9454545454545454,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04828031361103058,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9469790382244143,
"eval_overall_precision": 0.9458128078817734,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.235,
"eval_samples_per_second": 723.306,
"eval_steps_per_second": 12.764,
"step": 6432
},
{
"epoch": 68.0,
"grad_norm": 0.04871619492769241,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0134,
"step": 6528
},
{
"epoch": 68.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9221556886227544,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9447852760736196,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.962121212121212,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9548872180451128,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05099429935216904,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9405940594059405,
"eval_overall_precision": 0.9429280397022333,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2353,
"eval_samples_per_second": 722.511,
"eval_steps_per_second": 12.75,
"step": 6528
},
{
"epoch": 69.0,
"grad_norm": 0.2885429561138153,
"learning_rate": 1.55e-05,
"loss": 0.0151,
"step": 6624
},
{
"epoch": 69.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9262536873156342,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9345238095238095,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.047251880168914795,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9430693069306931,
"eval_overall_precision": 0.9454094292803971,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2334,
"eval_samples_per_second": 728.313,
"eval_steps_per_second": 12.853,
"step": 6624
},
{
"epoch": 70.0,
"grad_norm": 0.17146781086921692,
"learning_rate": 1.5e-05,
"loss": 0.0143,
"step": 6720
},
{
"epoch": 70.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9258160237388725,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9397590361445783,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05531075596809387,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9429280397022332,
"eval_overall_precision": 0.9476309226932669,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.234,
"eval_samples_per_second": 726.625,
"eval_steps_per_second": 12.823,
"step": 6720
},
{
"epoch": 71.0,
"grad_norm": 0.7716232538223267,
"learning_rate": 1.45e-05,
"loss": 0.0136,
"step": 6816
},
{
"epoch": 71.0,
"eval_LOCATION_f1": 0.927536231884058,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9230769230769231,
"eval_LOCATION_recall": 0.9320388349514563,
"eval_ORGANIZATION_f1": 0.9181286549707602,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9181286549707602,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.04589461535215378,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9395807644882861,
"eval_overall_precision": 0.9384236453201971,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2337,
"eval_samples_per_second": 727.513,
"eval_steps_per_second": 12.838,
"step": 6816
},
{
"epoch": 72.0,
"grad_norm": 0.14450299739837646,
"learning_rate": 1.4000000000000001e-05,
"loss": 0.0132,
"step": 6912
},
{
"epoch": 72.0,
"eval_LOCATION_f1": 0.941747572815534,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.941747572815534,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.923076923076923,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9341317365269461,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.052265413105487823,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9429280397022332,
"eval_overall_precision": 0.9476309226932669,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2344,
"eval_samples_per_second": 725.285,
"eval_steps_per_second": 12.799,
"step": 6912
},
{
"epoch": 73.0,
"grad_norm": 1.244653582572937,
"learning_rate": 1.3500000000000001e-05,
"loss": 0.0141,
"step": 7008
},
{
"epoch": 73.0,
"eval_LOCATION_f1": 0.9473684210526316,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9339622641509434,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9235294117647059,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9289940828402367,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9770992366412213,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9770992366412213,
"eval_PERSON_recall": 0.9770992366412213,
"eval_loss": 0.044290632009506226,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9469790382244143,
"eval_overall_precision": 0.9458128078817734,
"eval_overall_recall": 0.9481481481481482,
"eval_runtime": 0.2335,
"eval_samples_per_second": 728.039,
"eval_steps_per_second": 12.848,
"step": 7008
},
{
"epoch": 74.0,
"grad_norm": 0.20074079930782318,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.0141,
"step": 7104
},
{
"epoch": 74.0,
"eval_LOCATION_f1": 0.9423076923076923,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9401197604790419,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04744250327348709,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9443757725587144,
"eval_overall_precision": 0.9455445544554455,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2343,
"eval_samples_per_second": 725.458,
"eval_steps_per_second": 12.802,
"step": 7104
},
{
"epoch": 75.0,
"grad_norm": 1.6511667966842651,
"learning_rate": 1.25e-05,
"loss": 0.0127,
"step": 7200
},
{
"epoch": 75.0,
"eval_LOCATION_f1": 0.9473684210526316,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9339622641509434,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9285714285714285,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9454545454545454,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.052958231419324875,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9455445544554455,
"eval_overall_precision": 0.9478908188585607,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2339,
"eval_samples_per_second": 726.657,
"eval_steps_per_second": 12.823,
"step": 7200
},
{
"epoch": 76.0,
"grad_norm": 0.06270872801542282,
"learning_rate": 1.2e-05,
"loss": 0.0133,
"step": 7296
},
{
"epoch": 76.0,
"eval_LOCATION_f1": 0.941747572815534,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.941747572815534,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9262536873156342,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9345238095238095,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04870901256799698,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9442379182156135,
"eval_overall_precision": 0.9477611940298507,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2348,
"eval_samples_per_second": 723.868,
"eval_steps_per_second": 12.774,
"step": 7296
},
{
"epoch": 77.0,
"grad_norm": 0.22433413565158844,
"learning_rate": 1.1500000000000002e-05,
"loss": 0.0128,
"step": 7392
},
{
"epoch": 77.0,
"eval_LOCATION_f1": 0.9423076923076923,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9194029850746269,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9390243902439024,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.962121212121212,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9548872180451128,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05259751155972481,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9392812887236679,
"eval_overall_precision": 0.9427860696517413,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2339,
"eval_samples_per_second": 726.917,
"eval_steps_per_second": 12.828,
"step": 7392
},
{
"epoch": 78.0,
"grad_norm": 0.6566866636276245,
"learning_rate": 1.1000000000000001e-05,
"loss": 0.012,
"step": 7488
},
{
"epoch": 78.0,
"eval_LOCATION_f1": 0.9428571428571428,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9252336448598131,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9221556886227544,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9447852760736196,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05063054710626602,
"eval_overall_accuracy": 0.9886771610052472,
"eval_overall_f1": 0.9417596034696406,
"eval_overall_precision": 0.945273631840796,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2359,
"eval_samples_per_second": 720.663,
"eval_steps_per_second": 12.718,
"step": 7488
},
{
"epoch": 79.0,
"grad_norm": 0.5041309595108032,
"learning_rate": 1.05e-05,
"loss": 0.0117,
"step": 7584
},
{
"epoch": 79.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9226190476190477,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9393939393939394,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05141139775514603,
"eval_overall_accuracy": 0.9884009942004971,
"eval_overall_f1": 0.9416149068322981,
"eval_overall_precision": 0.9475,
"eval_overall_recall": 0.9358024691358025,
"eval_runtime": 0.2354,
"eval_samples_per_second": 722.3,
"eval_steps_per_second": 12.746,
"step": 7584
},
{
"epoch": 80.0,
"grad_norm": 0.3235592842102051,
"learning_rate": 1e-05,
"loss": 0.0107,
"step": 7680
},
{
"epoch": 80.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9194029850746269,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9390243902439024,
"eval_ORGANIZATION_recall": 0.9005847953216374,
"eval_PERSON_f1": 0.962121212121212,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9548872180451128,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05163806304335594,
"eval_overall_accuracy": 0.988124827395747,
"eval_overall_f1": 0.9379652605459058,
"eval_overall_precision": 0.942643391521197,
"eval_overall_recall": 0.9333333333333333,
"eval_runtime": 0.2343,
"eval_samples_per_second": 725.666,
"eval_steps_per_second": 12.806,
"step": 7680
},
{
"epoch": 81.0,
"grad_norm": 0.2620719373226166,
"learning_rate": 9.5e-06,
"loss": 0.0118,
"step": 7776
},
{
"epoch": 81.0,
"eval_LOCATION_f1": 0.951923076923077,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9428571428571428,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9285714285714285,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9454545454545454,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.962121212121212,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9548872180451128,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05169372633099556,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9455445544554455,
"eval_overall_precision": 0.9478908188585607,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2364,
"eval_samples_per_second": 719.115,
"eval_steps_per_second": 12.69,
"step": 7776
},
{
"epoch": 82.0,
"grad_norm": 0.21011920273303986,
"learning_rate": 9e-06,
"loss": 0.0111,
"step": 7872
},
{
"epoch": 82.0,
"eval_LOCATION_f1": 0.951923076923077,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9428571428571428,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9313432835820895,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9512195121951219,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.051322467625141144,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9490683229813665,
"eval_overall_precision": 0.955,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2346,
"eval_samples_per_second": 724.607,
"eval_steps_per_second": 12.787,
"step": 7872
},
{
"epoch": 83.0,
"grad_norm": 0.3934875428676605,
"learning_rate": 8.500000000000002e-06,
"loss": 0.0104,
"step": 7968
},
{
"epoch": 83.0,
"eval_LOCATION_f1": 0.951923076923077,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9428571428571428,
"eval_LOCATION_recall": 0.9611650485436893,
"eval_ORGANIZATION_f1": 0.9313432835820895,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9512195121951219,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9657794676806084,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9621212121212122,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05157596245408058,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9478908188585606,
"eval_overall_precision": 0.9526184538653366,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2355,
"eval_samples_per_second": 721.78,
"eval_steps_per_second": 12.737,
"step": 7968
},
{
"epoch": 84.0,
"grad_norm": 0.38065028190612793,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0131,
"step": 8064
},
{
"epoch": 84.0,
"eval_LOCATION_f1": 0.9523809523809522,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9345794392523364,
"eval_LOCATION_recall": 0.970873786407767,
"eval_ORGANIZATION_f1": 0.9309309309309309,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9567901234567902,
"eval_ORGANIZATION_recall": 0.9064327485380117,
"eval_PERSON_f1": 0.962121212121212,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9548872180451128,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.05147995054721832,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.946716232961586,
"eval_overall_precision": 0.9502487562189055,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2368,
"eval_samples_per_second": 717.854,
"eval_steps_per_second": 12.668,
"step": 8064
},
{
"epoch": 85.0,
"grad_norm": 0.8001857399940491,
"learning_rate": 7.5e-06,
"loss": 0.0128,
"step": 8160
},
{
"epoch": 85.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9317507418397626,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9457831325301205,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.962121212121212,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9548872180451128,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.049123797565698624,
"eval_overall_accuracy": 0.9889533278099972,
"eval_overall_f1": 0.9455445544554455,
"eval_overall_precision": 0.9478908188585607,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.235,
"eval_samples_per_second": 723.443,
"eval_steps_per_second": 12.767,
"step": 8160
},
{
"epoch": 86.0,
"grad_norm": 0.04900652542710304,
"learning_rate": 7.000000000000001e-06,
"loss": 0.0114,
"step": 8256
},
{
"epoch": 86.0,
"eval_LOCATION_f1": 0.9423076923076923,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9285714285714285,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9454545454545454,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04918617755174637,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9454094292803972,
"eval_overall_precision": 0.9501246882793017,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2352,
"eval_samples_per_second": 722.696,
"eval_steps_per_second": 12.753,
"step": 8256
},
{
"epoch": 87.0,
"grad_norm": 0.050100088119506836,
"learning_rate": 6.5000000000000004e-06,
"loss": 0.0104,
"step": 8352
},
{
"epoch": 87.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9317507418397626,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9457831325301205,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04836311936378479,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9478908188585606,
"eval_overall_precision": 0.9526184538653366,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2345,
"eval_samples_per_second": 724.815,
"eval_steps_per_second": 12.791,
"step": 8352
},
{
"epoch": 88.0,
"grad_norm": 0.28243932127952576,
"learning_rate": 6e-06,
"loss": 0.0117,
"step": 8448
},
{
"epoch": 88.0,
"eval_LOCATION_f1": 0.9371980676328503,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9326923076923077,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9285714285714285,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9454545454545454,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.050313472747802734,
"eval_overall_accuracy": 0.9892294946147473,
"eval_overall_f1": 0.9440993788819876,
"eval_overall_precision": 0.95,
"eval_overall_recall": 0.9382716049382716,
"eval_runtime": 0.2336,
"eval_samples_per_second": 727.863,
"eval_steps_per_second": 12.845,
"step": 8448
},
{
"epoch": 89.0,
"grad_norm": 0.140725240111351,
"learning_rate": 5.500000000000001e-06,
"loss": 0.0115,
"step": 8544
},
{
"epoch": 89.0,
"eval_LOCATION_f1": 0.941747572815534,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.941747572815534,
"eval_LOCATION_recall": 0.941747572815534,
"eval_ORGANIZATION_f1": 0.9317507418397626,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9457831325301205,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.050604552030563354,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9465838509316771,
"eval_overall_precision": 0.9525,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2346,
"eval_samples_per_second": 724.639,
"eval_steps_per_second": 12.788,
"step": 8544
},
{
"epoch": 90.0,
"grad_norm": 0.37635624408721924,
"learning_rate": 5e-06,
"loss": 0.0102,
"step": 8640
},
{
"epoch": 90.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9317507418397626,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9457831325301205,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04930723458528519,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.9478908188585606,
"eval_overall_precision": 0.9526184538653366,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2348,
"eval_samples_per_second": 724.161,
"eval_steps_per_second": 12.779,
"step": 8640
},
{
"epoch": 91.0,
"grad_norm": 0.24515359103679657,
"learning_rate": 4.5e-06,
"loss": 0.0108,
"step": 8736
},
{
"epoch": 91.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9317507418397626,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9457831325301205,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04927138239145279,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.9478908188585606,
"eval_overall_precision": 0.9526184538653366,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2335,
"eval_samples_per_second": 728.0,
"eval_steps_per_second": 12.847,
"step": 8736
},
{
"epoch": 92.0,
"grad_norm": 0.1399693638086319,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0106,
"step": 8832
},
{
"epoch": 92.0,
"eval_LOCATION_f1": 0.9423076923076923,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9333333333333333,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9285714285714285,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9454545454545454,
"eval_ORGANIZATION_recall": 0.9122807017543859,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.050085004419088364,
"eval_overall_accuracy": 0.9895056614194974,
"eval_overall_f1": 0.9454094292803972,
"eval_overall_precision": 0.9501246882793017,
"eval_overall_recall": 0.9407407407407408,
"eval_runtime": 0.2349,
"eval_samples_per_second": 723.818,
"eval_steps_per_second": 12.773,
"step": 8832
},
{
"epoch": 93.0,
"grad_norm": 0.5545656085014343,
"learning_rate": 3.5000000000000004e-06,
"loss": 0.0117,
"step": 8928
},
{
"epoch": 93.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9317507418397626,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9457831325301205,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04918910935521126,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.9478908188585606,
"eval_overall_precision": 0.9526184538653366,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2347,
"eval_samples_per_second": 724.334,
"eval_steps_per_second": 12.782,
"step": 8928
},
{
"epoch": 94.0,
"grad_norm": 0.24767446517944336,
"learning_rate": 3e-06,
"loss": 0.011,
"step": 9024
},
{
"epoch": 94.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9317507418397626,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9457831325301205,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04885171353816986,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.9478908188585606,
"eval_overall_precision": 0.9526184538653366,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.234,
"eval_samples_per_second": 726.551,
"eval_steps_per_second": 12.821,
"step": 9024
},
{
"epoch": 95.0,
"grad_norm": 0.38285189867019653,
"learning_rate": 2.5e-06,
"loss": 0.0098,
"step": 9120
},
{
"epoch": 95.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9317507418397626,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9457831325301205,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.050627708435058594,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.9478908188585606,
"eval_overall_precision": 0.9526184538653366,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2345,
"eval_samples_per_second": 725.08,
"eval_steps_per_second": 12.796,
"step": 9120
},
{
"epoch": 96.0,
"grad_norm": 0.07814586162567139,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.0114,
"step": 9216
},
{
"epoch": 96.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9401197604790419,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04947812855243683,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.946716232961586,
"eval_overall_precision": 0.9502487562189055,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2336,
"eval_samples_per_second": 727.75,
"eval_steps_per_second": 12.843,
"step": 9216
},
{
"epoch": 97.0,
"grad_norm": 0.053973570466041565,
"learning_rate": 1.5e-06,
"loss": 0.0095,
"step": 9312
},
{
"epoch": 97.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9401197604790419,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04963592812418938,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.946716232961586,
"eval_overall_precision": 0.9502487562189055,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2339,
"eval_samples_per_second": 726.887,
"eval_steps_per_second": 12.827,
"step": 9312
},
{
"epoch": 98.0,
"grad_norm": 0.4925645589828491,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.0105,
"step": 9408
},
{
"epoch": 98.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9401197604790419,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.0491667240858078,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.946716232961586,
"eval_overall_precision": 0.9502487562189055,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.235,
"eval_samples_per_second": 723.441,
"eval_steps_per_second": 12.767,
"step": 9408
},
{
"epoch": 99.0,
"grad_norm": 0.016408275812864304,
"learning_rate": 5.000000000000001e-07,
"loss": 0.0107,
"step": 9504
},
{
"epoch": 99.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9401197604790419,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.04960748925805092,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.946716232961586,
"eval_overall_precision": 0.9502487562189055,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2338,
"eval_samples_per_second": 727.113,
"eval_steps_per_second": 12.831,
"step": 9504
},
{
"epoch": 100.0,
"grad_norm": 0.030859585851430893,
"learning_rate": 0.0,
"loss": 0.0108,
"step": 9600
},
{
"epoch": 100.0,
"eval_LOCATION_f1": 0.9468599033816425,
"eval_LOCATION_number": 103,
"eval_LOCATION_precision": 0.9423076923076923,
"eval_LOCATION_recall": 0.9514563106796117,
"eval_ORGANIZATION_f1": 0.9289940828402367,
"eval_ORGANIZATION_number": 171,
"eval_ORGANIZATION_precision": 0.9401197604790419,
"eval_ORGANIZATION_recall": 0.9181286549707602,
"eval_PERSON_f1": 0.9694656488549618,
"eval_PERSON_number": 131,
"eval_PERSON_precision": 0.9694656488549618,
"eval_PERSON_recall": 0.9694656488549618,
"eval_loss": 0.049681250005960464,
"eval_overall_accuracy": 0.9897818282242474,
"eval_overall_f1": 0.946716232961586,
"eval_overall_precision": 0.9502487562189055,
"eval_overall_recall": 0.9432098765432099,
"eval_runtime": 0.2334,
"eval_samples_per_second": 728.375,
"eval_steps_per_second": 12.854,
"step": 9600
},
{
"epoch": 100.0,
"step": 9600,
"total_flos": 4325426924793372.0,
"train_loss": 0.04050279265269637,
"train_runtime": 503.2041,
"train_samples_per_second": 304.25,
"train_steps_per_second": 19.078
}
],
"logging_steps": 500,
"max_steps": 9600,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 500,
"total_flos": 4325426924793372.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}